## Why
A low-risk score for a later action could release an earlier pending Guardian review when the thread's score lag reached zero, bypassing that action's synchronous review result.
## What changed
Track the accepted score's source action and allow it to release a pending review only when it comes from that action or an earlier one. Keep cached-score approval available before synchronous review starts, but prevent the initial computer-use allowance from releasing an already pending review.
## Testing
Add an app-server regression test with two pending reviews: a later low-risk score approves its own action while the earlier action remains pending and honors its synchronous denial.
GitOrigin-RevId: ed8b9c4793b2538f634edfc5699797a6983358cc
## Why
A synchronous Guardian review could keep an action waiting even after an asynchronous score supplied valid low-risk evidence for approval.
## What changed
- In adaptive mode, race the synchronous review against score updates that satisfy the existing cached-approval checks, unless a fresh review is required.
- When asynchronous approval wins, cancel and drain the pending review, then revalidate the action and history lifetime and enforce cancellation and timeout limits before approving.
- Emit an approved review completion without a synchronous assessment or risk level, and use the cached-approval path for the final decision.
## Testing
Add an app-server regression case that holds the synchronous review pending, releases a low-risk score, and verifies approval completes without a risk level. Sequence existing scenarios to finish synchronous reviews before releasing classification results when they test synchronous evidence.
GitOrigin-RevId: 04f5ad6b960b819b565fccb1b85c8039ccbd0479
## What changed
- Limit multi-agent V2 `fork_turns` guidance to `all` and `none`. Accept legacy positive integer strings as full-history forks instead of truncating parent history.
- Remove partial-history fork handling and telemetry, and direct model override usage to `fork_turns: "none"`.
- Strip inherited `multi_agent.role_instructions` and `multi_agent.usage_hint` content by kind, including persisted hints whose wording predates the current bundled instructions.
## Testing
Update regression coverage for legacy `"1"` and `"3"` values inheriting full history, invalid and zero values being rejected, and stale parent hints being removed from compacted history with both marked and unmarked instructions.
GitOrigin-RevId: 8f6017dc66ad8deefd7745399ef76e1bb1435bb2
## Why
Messages with the `partial_answer` phase contain answer text without declaring a terminal answer. They should remain searchable and speakable without being treated as final messages.
## What changed
- Preserve explicit `partial_answer` phases in streamed and completed realtime handoffs, bypassing legacy channel-prefix parsing and routing them to the `speakable` channel.
- Treat partial answers as nonterminal in V1 handoffs and omit the final-message prefix.
- Include partial answers in thread occurrence searches and normalize them to the final conversation channel in rollout traces.
## Testing
Extend coverage for realtime phase routing, streamed and completed handoffs, partial-answer search results, and rollout normalization. Verify that turn summaries still exclude nonterminal messages.
GitOrigin-RevId: aa183da783f6e7e0b78ddd51073cba533297e121
## Why
Fast mode previously gated both Fast and Ultra Fast, preventing policies from allowing one while disabling the other.
## What changed
- Add the default-enabled `features.ultrafast_mode` flag and enforce it independently of `features.fast_mode` in service-tier selection, requests, and agent prewarming.
- Filter TUI service-tier commands and selections by the corresponding policy and model catalog support.
- Report `supportsIndependentSpeedModes: true` from `configRequirements/read` and update the protocol schemas and generated bindings. Retain the shared Fast gate when connecting to older servers that omit this capability.
- Preserve legacy cloud speed denials by translating `rbac-fast-mode` fragments with `fast_mode = false` into a denial of both modes, while retaining higher-priority enterprise overrides.
## Testing
Add coverage for all four Fast/Ultra Fast policy combinations in requirements responses and request routing, agent prewarm inheritance, TUI command visibility and saved selections, and legacy cloud denial normalization and override precedence.
GitOrigin-RevId: 147e08524c4b228ea9d46b25a9f8aa64c359e169
## What changed
- Remove `instructions_variables`, its protocol type, and unused personality templates. Continue accepting older catalogs by ignoring their legacy variables.
- Report `supports_personality` as `false` in app-server model listings and TUI model presets.
- Preserve pinned model metadata and base instructions when only personality settings change. Reuse Guardian review sessions across friendly and pragmatic settings, while keeping the `none` opt-out distinct.
## Testing
Update coverage for legacy catalog deserialization, personality override notifications, opt-out behavior during model switches, and preservation of instructions and history on resume.
GitOrigin-RevId: bee8a263ef84046301888d02347f43929ececce9
## What changed
Introduce `TurnEnvironmentRequest` for caller-supplied environment input and construct `TurnEnvironmentSelection` at session startup and app-server settings boundaries. Update thread startup, default environments, and inherited environment handoffs to use requests, with explicit conversions when reusing runtime selections.
Move the environment types into `protocol::environment` while retaining their `protocol` re-exports. Update test fixtures and existing tests to build request inputs separately from runtime selections.
GitOrigin-RevId: 12e7daaece95aae136afae8b055b4dbaebdffc75
## What changed
- Carry opaque `review_target` values through misalignment errors and expose optional `reviewTarget` in the app-server protocol and generated clients. Preserve the value verbatim and redact it from debug output.
- Keep target-based `misalignment_override` metadata on turn requests, preserve it across steering updates, and exclude it from compaction and external MCP metadata. Reject overrides from global Responses metadata while retaining legacy timestamp behavior for per-turn overrides.
## Testing
Extend coverage for error propagation, debug and rollout redaction, steering preservation, and metadata filtering. Verify that automatic compaction omits the review target while turn requests before and after compaction retain it.
GitOrigin-RevId: 8c1abb076a206ff5927a4acc31bd25e3efc2bff9
## Why
Updating a CRLF file with `apply_patch` previously normalized its line endings to LF unless preservation was explicitly enabled. Preserve the file's existing line endings without requiring an opt-in.
## What changed
- Use line-ending-preserving updates for both tool calls and standalone `apply_patch` invocations, removing the legacy normalization mode.
- Mark `apply_patch_preserve_line_endings` as removed.
- Always set `CODEX_APPLY_PATCH_PRESERVE_LINE_ENDINGS=1` in child environments for compatibility with older patch executables, overriding stale values.
## Testing
Update CLI, tool-call, shell-heredoc, and app-server tests to check CRLF preservation by default. Keep coverage for overriding stale compatibility environment values.
GitOrigin-RevId: 96d0b0e5350faa3fc7a45d63627a132657b44523
## What changed
Support `browser_use.extension.request_headers` as a list of `name`/`value` pairs and expose it through `config/requirements/read` as `browserUse.extension.requestHeaders`. Update the generated JSON schemas, TypeScript types, and Python models.
Preserve header values, including template strings, verbatim. Higher-priority requirement layers replace the entire header list, including with an explicit empty list. Redact header values in Rust debug output while retaining them in API serialization.
## Testing
Add coverage for parsing and malformed entries, extension scoping, empty-list overrides, API mapping and read responses, and debug redaction without changing serialized values.
GitOrigin-RevId: 02299e82a91aa863966d0277091bc5e8cc1ebe07
Extend the app-server thread metadata test to archive a thread after pinning
and unpinning it, before any turn starts. Assert that the thread appears in
`thread/list` results with `archived: true` and `use_state_db_only: true`.
GitOrigin-RevId: dde58e892b28843870bc3f678134fc86b93cd79c
## What changed
- Accept per-environment `skills.required` lists through `environment/add` and `environments.toml`.
- Before inference, require each named skill to be enabled and supplied by the selected environment. Missing skills fail the turn before a model request, including when environment setup fails.
- Stop applying an environment's requirements after it is deselected. Exempt isolated Guardian reviewers, which have no skill catalog.
## Testing
Add tests for available, missing, disabled, and wrong-environment skills, failed environment setup, recovery after deselection, and propagation of TOML requirements to the correct environment.
GitOrigin-RevId: 302ced4774697d2f414f745fe0535e71f747eda2
## Why
Snapshot classifier requests can arrive out of order, so continuation tests need to keep the next tool blocked until the current tool's classifier request has been captured and checked.
## What changed
Gate every mock Guardian review in high-risk review continuation scenarios. Release each review after checking the corresponding classifier request, preserving the ordering needed by the existing assertions.
GitOrigin-RevId: 9e52acd2bb1ce2fb71100fe0e1b92304d29e9634
## Why
When `flush_transcript_tail_on_session_end` is enabled, remaining speech must be available in thread history as soon as realtime closure is reported, even while a model response is still running. Saving that transcript should not trigger another model request.
## What changed
Record the transcript tail directly in model and client history, attaching it to the active turn or creating a completed history turn when idle. Flush persistence before emitting `RealtimeConversationClosed`, and keep realtime context active until recording finishes so the return to text instructions follow the transcript.
## Testing
Extend core and app-server tests to cover immediate history visibility in paginated and legacy modes, idle and active turns, closure without extra inference, transcript reuse in subsequent text turns, and interruption after closure.
GitOrigin-RevId: ae323b711f22aa88db1432e24ad4bb3eb3f08f6b
## Why
Bedrock catalogs cleared all service-tier metadata, and requests omitted every selected tier. This prevented users from selecting `ultrafast` or using tiers defined in custom catalogs.
## What changed
- Advertise `ultrafast` for `openai.gpt-6-astra` on Mantle and the `global.openai.gpt-6-astra` and `us.openai.gpt-6-astra` Runtime variants, while retaining the implicit default tier unless users select otherwise.
- Preserve custom catalog speed tiers, service-tier definitions, and defaults while continuing to normalize Bedrock web search compatibility.
- Send selected service tiers only when the Bedrock model advertises them, including `flex`.
## Testing
Add coverage for `model/list` tier discovery, custom catalog preservation, configured and per-turn HTTP request tiers, and TUI slash-command selection, toggling, and model switching.
GitOrigin-RevId: 4793e7af7b9f604a6b7812611030da6adb8acd35
## What changed
- Remove `namespace_tools` from `ProviderCapabilities` and `namespaceTools` from `ModelProviderCapabilitiesReadResponse`, updating generated schemas and SDK types.
- Preserve tool namespaces and configured collaboration tool namespaces without a provider capability check, and always use Responses Lite tool serialization for Responses Lite requests.
- Gate tool search on `supports_search_tool` and retain the existing image generation and web search checks without requiring a namespace capability.
GitOrigin-RevId: ae1843563736765a40e03a02c41ff5e470018a93
## Why
`thread/attachment/list` lists attachments for a known thread. Clients also need to find the threads associated with a given attachment identity.
## What changed
Add `thread/attachmentOwner/list` to return owning thread IDs and archive status for an exact `attachmentType` and `identityKey`. Support cursor pagination and an optional `archived` filter, including both archived and non-archived threads by default.
Wire the request through the thread store and update documentation, protocol schemas, and generated TypeScript and Python types. The lookup is limited to the configured thread store and reports current membership, not an atomic resource-cleanup check.
## Testing
Extend app-server integration tests to cover exact type-and-key matching, multiple owners, archive filtering, and invalid cursor rejection.
GitOrigin-RevId: 30f4a20e00243d0023246d465a9b95213b3adeb6
## Why
Concurrent Linux test spawns can inherit writable descriptors for executable fixtures, preventing those fixtures from being executed even after the writing test closes its descriptor.
## What changed
Replace direct executable fixture writes and copies across the Rust tests with `codex_utils_cargo_bin::write_executable` and `copy_executable`. These existing helpers complete writes and copies in separate processes on Linux.
Remove the empty temporary inode before creating fake bubblewrap executables, and stage tampered bubblewrap bytes in a separate data file before copying them into the executable fixture. Add the required test dependencies.
GitOrigin-RevId: c875c83088731a4933ef1574e8d79d8cecc12f54
## Why
The rolling retained-context window can change as assistant messages are added or evicted. Placing it before the transcript invalidates the reusable history prefix.
## What changed
Move retained user instructions and context after the transcript and action-specific attestations, immediately before the planned action in asynchronous Guardian requests. Keep synchronous section ordering unchanged.
## Testing
Extend the cache-prefix regression test to cover retained assistant message growth and eviction alongside changing attestations. Update app-server and async scorer assertions to verify the new request ordering.
GitOrigin-RevId: 59953d582d4b174ce3e083606626c7532ce0776d
## Why
Background code-mode cells can continue running after a new turn starts. Looking up grants and strict review requirements through the active turn can make those cells lose their approved access or use another turn's permissions.
## What changed
- Keep turn-scoped grants and strict review state in `TurnContext`, retained by captured steps and background cells.
- Record permission responses against the requesting turn, including requests made after a later turn starts.
- Share live session-scoped grants across turns while keeping turn-scoped grants isolated.
- Use the originating turn's permissions and review requirements for tool execution, patches, MCP calls, file uploads, and terminal input.
## Testing
Add regression coverage for background cells retaining grants across turn changes, turn versus session scope, permission requests after the next turn starts, and strict review enabled while `write_stdin` is queued.
GitOrigin-RevId: 641502fbfd43553c2c42424d4aaa53ae8020c850
## Why
Detached launches truncate stderr logs, losing details from previous failures. Updater handoffs can also leave existing writers with stale offsets after truncation.
## What changed
- Record daemon lifecycle and update stages with timings, outcomes, and typed OS errors, omitting error messages and context.
- Preserve the last 256 KiB of nonempty stderr logs before truncation and use append handles to prevent gaps during handoff. Preservation failures do not block launch.
- Attach current and previous updater log tails when log inclusion is enabled for a report, with a 512 KiB total limit and legacy filename fallback. Skip missing, empty, and nonregular files.
## Testing
Add regression coverage for diagnostic error redaction, bounded log preservation, append behavior during handoff, attachment selection, and updater logs in captured report uploads.
GitOrigin-RevId: 918317022ab9dcfd1b13d676872706c77e9ffbb2
## What changed
Add the experimental `account/bedrock/checkGovCloudRequirements` RPC so clients can check the active Bedrock configuration after login or setup. It returns `isGovCloud` and `shouldWarn`, warning for GovCloud when managed requirements lack API-only login or enabled application network restrictions with an explicit allow entry for the active endpoint domain.
Reload configuration and requirements on each check while preserving the current session's authentication. Official Bedrock endpoint hostnames determine the region; otherwise, resolve it using the current authentication state. Non-Bedrock providers and commercial regions return both fields as `false`; configuration and region resolution failures return RPC errors. The check is advisory and does not block login or certify the entire network configuration.
## Testing
Add integration coverage for configuration and requirements updates without a restart, login changes, unreadable saved credentials, Mantle and Runtime endpoints, custom proxies, official endpoint region precedence, and invalid requirements.
GitOrigin-RevId: 24bfa91326cf5c73ada176c47351445de91b60a0
## What changed
- Mark `api_key_model_discovery` as stable and enable it by default, while preserving explicit user opt-outs and provider catalog requirements.
- Fall back to bundled models when discovery is disabled at runtime, including when a remote catalog has already been loaded.
## Testing
Extend model-list coverage for default enablement, app overrides, and user configuration precedence. Add a regression assertion that runtime opt-outs hide loaded catalogs without additional fetches, and update daemon compatibility tests for the new default.
GitOrigin-RevId: feaf732757792cc58063f21a5327d0e633f079f4
## Why
Guardian review continuations can repeat retained-instruction omission notices even when availability has not changed. When retained context becomes complete, earlier notices also need to be superseded explicitly.
## What changed
Track delivered user-instruction and assistant-context omission states in host metadata scoped to the retained-instructions section. Suppress redundant notice-only sections when the state is unchanged, and emit an availability-change notice when an earlier omission clears, including when no retained originals remain.
Treat missing delivery metadata as unknown. Matching notice text in coalesced tool output cannot establish host delivery, and incomplete history entries discard omission delivery proof.
## Testing
Add coverage for repeated notices, independent histories, availability recovery, and matching notice text in multimodal REPL output. Extend app-server review-continuation tests to assert that each effective classifier context contains the retained user-instruction omission notice exactly once.
GitOrigin-RevId: c6d52dd1dafb284af34b46174aecc7c8cc9b8404
## Why
Retained Guardian classifier conversations already contain previously delivered synchronous reviews. Appending those reviews again repeats evidence and consumes input budget.
## What changed
Track each review completion with a stable identity in host-only history metadata. Filter already delivered reviews before composing and budgeting continuation input, while preserving distinct completions even when their text is identical.
Fresh conversations receive the review evidence again, and shortened messages no longer count as complete delivery. Delivery metadata stays out of model requests.
## Testing
Add coverage for delivering retained reviews once, appending newly completed reviews, restoring evidence after failed streams, and retaining reviews when history lacks complete delivery metadata.
GitOrigin-RevId: b8d58ffdd7d9c484676af707c65fa50020aae73c
## What changed
- Add `features.guardianv2.async_classifier_mode` with `snapshot` and `conversation` modes. Local configuration overrides model defaults; snapshots remain the fallback.
- Retain completed classifier requests and responses in conversation mode, appending transcript deltas without repeating previously delivered user instructions.
- Rebuild retained history when authorization, classifier instructions, or parent compaction changes, after an incomplete response, or when the next request exceeds the configured token limit. Add `async_classifier_conversation_token_limit`, defaulting to 100,000 tokens, while preserving the model's input limit for fresh requests.
- Serialize conversation requests in observation order, bound outstanding work, and reject stale work after authorization changes or thread shutdown. Record retained and new input token costs.
## Testing
Add tests for configuration precedence, history reuse and resets, ordered admission, queue overflow, and stale or stopped requests. Exercise the approval matrix in both modes, including resume, fork, mandatory review, authorization changes, and stream failure after an early score.
GitOrigin-RevId: 35b9800104648cde4f467086e678dee12458c3e5
## Why
Naming a paginated thread before its first turn must make it durable so it can be resumed immediately and after an app-server restart.
## What changed
Persist the live rollout before updating name metadata in SQLite. Propagate persistence failures before saving the name.
## Testing
Add thread-store tests for empty-thread persistence and failure handling, plus an app-server regression test that resumes a named empty thread before and after a restart and completes its first turn.
GitOrigin-RevId: 2f7556c7de65f6a86177130c39e1a17951496931
## What changed
Allow API-key sessions using the OpenAI provider to forward explicit cyber access programs when `features.api_key_cyber_access_programs` is enabled, regardless of `features.api_key_model_discovery`.
## Testing
Expand the app-server test to cover all four combinations of the two feature flags, checking forwarded programs and failures when forwarding is disabled. Default the API-key test helper to model discovery disabled.
GitOrigin-RevId: f9cf1d2bd7c231645d50178cc6721b55a8d63268
## Why
A database can open successfully while containing corruption that startup previously missed. Detecting it before runtime initialization completes allows recoverable databases to be rebuilt while preserving the damaged files.
## What changed
- Run `PRAGMA quick_check(1)` when opening writable databases, with a 100 ms scan budget. Share attempts across cloned `SqliteConfig` instances by file identity so repeated opens skip validation and replacement files are checked again.
- Back up and rebuild runtime databases that support recovery. Report corruption without rebuilding thread history or other databases without an automatic recovery policy. Treat interrupted or locked checks as incomplete rather than confirmed corruption.
- Collect startup backups across recovery retries and include their locations in the app server warning. Explain that saved conversations can restore the thread list and history, while some database-only metadata may be unavailable.
- Record confirmed corruption in `codex.sqlite.corruption.count`.
## Testing
Add tests for recovery policies, backup preservation, validation caching and concurrency, cancelled and interrupted checks, and locked databases. Add app server coverage for recovery warnings and saved conversation restoration, a TUI warning snapshot, and message board post preservation.
GitOrigin-RevId: 43e26328888e0301def642d69bd324acee867566
## What changed
Register `in_app_voice` as a stable, default-enabled feature and add it to the configuration schema. The gate is intended for managed requirements to control permission for voice in desktop apps; permission does not establish voice availability or provider support.
## Testing
Add app-server coverage for reporting `in_app_voice = false` from `requirements.toml` in both requirements and feature-list responses. Extend the CLI feature-list test to verify that cloud-managed requirements disable the gate despite a user-configured `true` value, without rewriting the user configuration.
GitOrigin-RevId: 6ec3bc0176fdb3e1714b0136bf812bd56591f6a1
## Why
User goal edits and clears need to reach the model as user instructions, including when a thread is unloaded or history is being compacted. Automatic goal lifecycle updates must not supply user authorization.
## What changed
- Add optional `origin` values of `user` and `automatic` to `thread/goal/set` and `thread/goal/clear`, and mark TUI goal requests as user actions. Omitted origins do not supply user authorization.
- Persist explicit user objective, status, and clear instructions before changing goal state. Recording failures leave goal state unchanged.
- Coordinate goal edits with thread resume, reload stored history under writer ownership, and preserve edits accepted after the compaction input snapshot.
- Update generated protocol schemas and TypeScript and Python bindings.
## Testing
Add coverage for user edits and clears on loaded and unloaded threads, concurrent path-based resume, exclusion of automatic goals from user instructions, preservation of edits during compaction, and recording failures that leave goal state unchanged.
GitOrigin-RevId: d779d7c678a0c32a6ef76975dbe5b1400d1df245
## What changed
Forward explicit `cyberAccessProgram` selections for the built-in OpenAI provider when both `api_key_cyber_access_programs` and `api_key_model_discovery` are enabled. The new feature defaults to disabled and can be toggled through the app server's experimental feature enablement API.
Reject explicit selections in OpenAI API-key sessions when either feature is disabled, instead of silently omitting the program. Leave entitlement and model restrictions to the server, and preserve the requested program when a server rejection triggers transport retries.
## Testing
Add app-server coverage for both feature gates, forwarding all three program values, and server rejection without fallback. Update core coverage for API-key resumes with disabled features and custom-provider omission.
GitOrigin-RevId: aa639afb841aa651b28f6f3f61198299372baa2d
## Why
Successful file fallback can hide a secure-store failure. Storage diagnostics need to distinguish that fallback from explicit file storage while keeping credential values out of error output.
## What changed
- Record credential load, save, delete, and fallback-file cleanup outcomes, including secure-store failures and fallback reasons.
- Preserve the initiating client's attribution across app-server requests, login tasks, sessions, turns, and blocking token persistence.
- Preserve storage error context and typed causes while redacting credential JSON data errors and payload-bearing keyring errors.
- Include sanitized fallback completion warnings in the default `codex login` file logs.
## Testing
Add coverage for storage policy and metric attribution, credential redaction, login diagnostics, concurrent app-server clients, device-code login, and token refresh during a turn.
GitOrigin-RevId: 6d5651c1718d184016fa77befa02aa528750b2ae
## What changed
Add `openai.gpt-6.1-sol` to the Bedrock Mantle catalog and its `global.` and `us.` variants to the Bedrock Runtime catalog. Make GPT-6.1 Sol the default and provider fallback model, preferring the global variant for Runtime. Keep existing models available.
## Testing
Update catalog and provider assertions, thread-start fallback tests, and TUI model-picker snapshots to cover GPT-6.1 Sol and the new defaults.
GitOrigin-RevId: ec65744ff9409980474cc1faf516beed0b2430da
## Why
Stale thread capability roots can reconnect executors that are not selected for the current turn and shadow selected roots with the same ID.
## What changed
Filter out roots whose environments are absent from the turn snapshot before deduplication and readiness resolution. Update app-server capability tests to explicitly select the executor environments used by each turn, including after resume.
## Testing
Add regression coverage for full-access and workspace-write permissions, verifying that stale roots never connect an unselected executor, selected roots with matching IDs remain available, and turns with no environments expose no roots.
GitOrigin-RevId: afe375047cc5e8aad06df83334149510460dcdcc
## Why
The app server previously rejected OAuth login for enterprise-managed MCP servers. These servers need an explicit sign-in flow that ties saved authorization to the active Codex user and workspace and prevents canceled or superseded attempts from saving credentials.
## What changed
- Enable enterprise sign-in through `mcpServer/oauth/login` for configured servers with a connected thread, trusted IdP registration, and `features.use_xaa` enabled. Scope shared enterprise credentials by user, workspace, issuer, and client ID.
- Add `loginId` to MCP OAuth login responses and completion notifications, preserving compatibility with older servers that omit it.
- Support enterprise login replacement and `account/login/cancel`, wait for callback listener shutdown before replacement, and recheck account and configuration before saving grants. Fence stale attempts across processes and account changes.
- Remove shared enterprise authorization during account logout and `codex mcp logout`, including when the feature is disabled. Continue account logout if enterprise cleanup fails, and invalidate MCP runtimes on account changes.
Start a fresh session after successful enterprise sign-in to use the saved grant.
## Testing
Add regression coverage for login replacement and cancellation, callback port reuse, account changes during setup, cross-process logout invalidation, persisted workspace policy selection, cleanup failures, and responses from older servers without `loginId`.
GitOrigin-RevId: 7ed4caaab4659ed1e67064262cf5cee48e3a26ac
## Why
Configuration reloads must honor current managed restrictions without granting new enterprise MCP authority to existing sessions or overwriting newer configuration with stale snapshots.
## What changed
- Allow enterprise managed authentication only for configured MCP servers. Remove plugin `ema_auth` overlays from the schema and disable servers that still use them.
- Refresh ordinary MCP settings while preserving session settings and initially admitted enterprise registrations. Disable enterprise MCP when its registration changes, policy revokes access, or configuration loading or resolution fails; require a new session to restore enterprise authority.
- Publish refreshes only when their captured configuration is still current, with bounded retries in app-server reloads. Preserve updated managed restrictions even when a refresh is rejected.
- Finish processing other thread refreshes before `config/mcpServer/reload` reports a rejection, and document that an error can accompany partially applied changes.
## Testing
Add regression coverage for stale refreshes, bounded retries, managed-policy revocation, persistent enterprise disablement, ordinary MCP transport changes, and rejection of plugin enterprise authentication. Verify that denied enterprise servers receive no requests.
GitOrigin-RevId: 34429cd339c1ec152a2ee8697cb29f0cff5d9e5f
## Why
Providers with `model_catalog_url` could advertise bundled models absent from their catalog or reuse stale models after a failed refresh. Model metadata could also match by prefix or namespaced suffix instead of the provider's exact model ID.
## What changed
- Suppress bundled model fallback and merging for explicit provider catalogs, including when discovery is disabled.
- Require unique, non-empty catalog slugs and match metadata by exact model ID.
- Serialize explicit catalog refreshes and invalidate in-memory and persisted catalog entries after fetch failures, preventing stale cache reuse.
- Report a clear configuration error when startup has no available model, while allowing an explicitly configured `model`.
## Testing
Add regression coverage for exact model matching, hidden catalog entries, cache invalidation across restart and recovery, invalid slugs, and empty-catalog startup with and without an explicit model. Update app-server model-list expectations and verify the TUI configuration error.
GitOrigin-RevId: ac323a94178e3c48df8d4a159a86fdbac20b03a2
## Why
Responses stopped by `content_filter` previously followed generic stream-error retry handling without guidance about the block. Retried requests need instructions to explain the limitation and offer a permitted alternative.
## What changed
- Recognize content-filter failures as a distinct error while preserving retryability and the existing public error representation.
- Append developer guidance to the conversation after each sampling block, retaining delivered output and using the existing retry handling.
- Support a model catalog override through `model_messages.content_filter_guidance`. Missing, null, blank, or values exceeding 512 UTF-8 bytes fall back to bundled guidance.
- The bundled guidance tells the model to avoid reproducing or working around blocked content, briefly explain the limitation, offer a permitted alternative, and continue unrelated authorized work.
## Testing
Add a scenario and request-history snapshot covering repeated blocks, catalog guidance on each retry, retained partial output, and eventual completion. Add error-mapping assertions for retryability, public error classification, and error text.
GitOrigin-RevId: ba0c201b3a5a3acf5cfa971332027240e0690225
## Why
Repeated plugin discovery and loading reparse unchanged manifests and repeat warnings for invalid fields.
## What changed
- Share a manifest cache through `PluginStore` across marketplace listing, plugin loading, capability inspection, and tool suggestion metadata.
- Reuse successful parses by plugin root, manifest path, and content digests, including the Codex overlay. Reread files on each load so manifest edits and overlay changes or removal remain visible.
- Bound the cache to 128 entries and bypass caching for inputs larger than 64 KiB. Retry failed parses and share entries across store clones while keeping independent stores isolated.
- Reuse loaded manifest data when loading apps and MCP metadata.
## Testing
Add unit coverage for parse reuse, warning deduplication, revision invalidation, repair after parse failures, equivalent Windows paths, store isolation, and oversized inputs. Add an app-server regression test that verifies repeated `plugin/list` requests observe manifest and overlay revisions in one running server.
GitOrigin-RevId: ed082cd7d198015cd8ed35db7f2af74e13f49915
## Why
Fresh threads have no rollout until their first turn, so archiving them previously failed with a missing-rollout error.
## What changed
Persist loaded, non-ephemeral threads before looking them up for archival. This lets a newly started thread be archived without creating a user turn.
## Testing
Update the archive regression test to cover threads with no turns in both legacy and paginated history modes. Verify the archive notification, empty turn history, `NotLoaded` status, and archived rollout path.
GitOrigin-RevId: 507351c6238ad96f5e3ffbd2ed7f432058e3d52c
## Why
Guardian denial-limit interruptions lack a structured error identifying the cause. Make this opt-in because older clients may not recognize the new error in shared history.
## What changed
- Add `auto_review.circuit_break_action = "strict"` to attach `TooManyDenials` to the interrupted turn. The default leaves the error unset.
- Expose `turn.error.codexErrorInfo = "tooManyDenials"` in app-server notifications and saved history, and update protocol schemas and generated types.
- Preserve the warning, denial limit, and interrupted status without emitting a separate error notification.
## Testing
Add an integration test covering omitted, `default`, and `strict` settings, checking warnings, live turn errors, the absence of separate error notifications, and persisted turn errors after restart.
GitOrigin-RevId: cb5d379e64728d4d7b9daf834c13756e4a70db31
## Why
Inspecting one MCP server should not require full-inventory discovery or a separate connection when a thread already has one.
## What changed
- Add optional `serverName` to `mcpServerStatus/list` and update generated schemas and bindings.
- With `threadId`, apply any pending runtime refresh and reuse the thread's current connection and tool catalog, waiting only for the selected server during discovery.
- Without `threadId`, create a discovery connection for only the selected server. Unknown names return an empty page; omitting `serverName` preserves full-inventory discovery.
## Testing
Add a regression test covering both status detail modes, checking that tool metadata is preserved and that status reads do not repeat `initialize` or `tools/list` requests.
GitOrigin-RevId: 1b361b67a993ab45cae493e88c146f50cfaf753a
## Why
Guardian reviews need to retain original evidence across parent compaction when checkpoint reuse is disabled, including after resume and rollback.
## What changed
- Make disabling `guardian_reuse_parent_compaction` select a bounded, independent review transcript while preserving thread-owned authorization.
- Keep synchronous reviews and asynchronous scoring independent of parent checkpoints, and allow reviewer sessions to continue using transcript deltas across parent compaction.
- Persist transcript entries with rollback provenance while remaining compatible with older checkpoint readers and metadata-free checkpoints.
- Exclude compaction output from the transcript and synthetic summaries from rollback turn boundaries. Use acceptance ordering to remove rolled-back evidence even when persistence order differs.
## Testing
Add regression coverage for reviewer continuity, evidence retention across compaction and resume, rollback after local and remote compaction, and checkpoint serialization compatibility.
GitOrigin-RevId: fea0852cc5537372854f4a34bacb6bfda6d13e88
## What changed
- Delete the `plugin-creator` skill, its assets, reference docs, helper scripts, and associated Python tests.
- Update the app-server skills context budget warning test to expect six omitted skills instead of seven.
GitOrigin-RevId: 005b1ab7f2f7c2933e6c297d01541746cc489f68
## Why
Changes in executor availability can alter cloud skill catalog rendering under a shared budget and repeat an unchanged executor catalog when it reconnects.
## What changed
- Cap cloud skills at three quarters of the metadata budget initially, leaving the remaining budget and unused cloud allowance for filesystem skills. Reduce the cloud cap only when doing so allows all skill entries to fit; description truncation alone does not trigger rebalancing.
- Persist the allocation across disconnects, compaction, and thread resume. Recompute it when the cloud inventory or total budget changes.
- Emit a short availability update when an unchanged selected-environment catalog returns and its full text remains in history. Reinject the full catalog when that text is missing.
## Testing
Add coverage for allocation stability, catalog and budget changes, omission handling, and full catalog reinjection after compaction and resume. Extend the selected capability stack test to verify reconnection avoids repeating the catalog.
GitOrigin-RevId: 839fe98024e00c4082a46e6a40675e15fd2c16c6
## Why
Archived threads without previews were filtered out of thread listings, even though they had valid session metadata.
## What changed
- Include archived threads with empty previews in both SQLite and rollout-file listings.
- Add archive-specific indexes for creation, update, and recency ordering so these listings can use indexed pagination.
## Testing
Add regression coverage for paginated archive listings with and without SQLite, archive query plans that avoid temporary sorting, and metadata reads that preserve source and file timestamps for empty archived threads.
GitOrigin-RevId: e29d0257b2e029bea5fdf94eed6dab1006d2a8f2
## Why
Usage limit errors discarded the server-selected window responsible for the limit, leaving turn and compaction analytics unable to distinguish five-hour limits from weekly limits.
## What changed
Preserve optional `limit_window_minutes` from usage limit error responses in `UsageLimitReachedError` and report it as `usage_limit_window_minutes` in turn and compaction events. Accept unsigned integers that fit in `u16`; treat missing, null, malformed, or out-of-range values as unknown. Events for other error kinds report `null`.
## Testing
Add coverage for HTTP and wrapped WebSocket error mapping, analytics serialization and reduction, and app-server propagation to turn and local/remote compaction events. Cases include five-hour and weekly windows, missing or invalid values, and unrelated errors.
GitOrigin-RevId: a32066a007559d91a3c868a756bfd0f976777176
## What changed
Allow `cursor` to accept an item anchor such as `{"type":"item","itemId":"item-123"}` with a non-empty `turnId`. Ascending pagination returns items after the anchor; descending pagination returns items before it. The anchor itself is excluded, and subsequent pages use the returned opaque string cursor.
Resolve anchors within the requested turn's visible history, including inherited fork history. Reject missing turn IDs and empty, unknown, or out-of-scope item IDs with invalid params (`-32602`). Preserve existing string and null cursor behavior, and update the protocol schemas, TypeScript and Python types, and API documentation.
## Testing
Add protocol round-trip and invalid-shape tests, app-server coverage for anchored pagination and errors, and thread-store coverage for growing turns, reverse pagination, page boundaries, fork visibility, and anchor scope validation.
GitOrigin-RevId: a74cea190d3ff1b44865429f8b0650b793eb688d
## Why
Cached executor MCP declarations must not gain access to host environment credentials when reconnecting to an executor that lacks environment credential resolution.
## What changed
- Retain credential policy through MCP registration, catalog materialization, and runtime setup. Derive selected HTTP plugin policy from the plugin's source environment.
- Reject host bearer-token fallback and transports requiring host environment headers or helpers for executor-owned declarations. Preserve host-configured credential resolution.
- Include credential policy in connection and tool catalog cache identities, and avoid reading host environment values for executor-only identities.
## Testing
Add regression coverage for legacy executors, cached declarations after a capability downgrade, policy preservation through catalog rebuilds, and connection and tool cache isolation.
GitOrigin-RevId: 2d5b85e4e98668c637c538cbe528914c936bd831
jif